A Parallel, O(N) Algorithm for Unbiased, Thin Watershed
| Autor: | Matthieu Faessel, Michel Bilodeau, Petr Dokládal, Théodore Chabardès |
|---|---|
| Přispěvatelé: | Centre de Morphologie Mathématique (CMM), MINES ParisTech - École nationale supérieure des mines de Paris, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL) |
| Jazyk: | angličtina |
| Rok vydání: | 2016 |
| Předmět: |
Watershed
Pixel Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Linear time 02 engineering and technology Iterative reconstruction Local implementation Segmentation Computer Science::Computer Vision and Pattern Recognition [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing [MATH.TR-IMG]Mathematics [math]/domain_math.tr-img Morphological segmentation Time complexity Algorithm ComputingMilieux_MISCELLANEOUS |
| Zdroj: | IEEE International Conference on Image Processing IEEE International Conference on Image Processing, Sep 2016, Phoenix, United States HAL ICIP |
| Popis: | International audience; The watershed transform is a powerful tool for morphological segmentation. Most common implementations of this method involve a strict hierarchy on gray tones in processing the pixels composing an image. Those dependencies complexify the efficient use of modern computational architectures. This paper aims at answering this problem by introducing a new way of simulating the waterflood that preserves the locality of data to be processed. We propose a region growth algorithm based on arrowing graphs that is strictly linear despite the valuation domain of input images. Simultaneous and disorderly growth is made possible by using a synchronization mechanism coded directly on the weight of nodes. Experimental results show that the algorithm is accurate and by far outperforms common watershed algorithms. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|